Neuromorphic Circuit for Temporal Odor Encoding in Turbulent Environments

Natural odor environments present turbulent and dynamic conditions, causing chemical signals to fluctuate in space, time, and intensity. While many species have evolved highly adaptive behavioral responses to such variability, the emerging field of neuromorphic olfaction continues to grapple with the challenge of efficiently sampling and identifying odors in real-time. In this work, we investigate metal-oxide (MOx) gas sensor recordings of constant airflow-embedded artificial odor plumes. We discover a data feature that is representative of the presented odor stimulus at a certain concentration, irrespective of temporal variations caused by the plume dynamics. Furthermore, we design a neuromorphic electronic nose front-end circuit for extracting and encoding this feature into analog spikes for gas detection and concentration estimation. The design is loosely inspired by the spiking output of parallel neural pathways in the mammalian olfactory bulb (OB). We test the circuit for gas recognition and concentration estimation in artificial environments, where either single gas pulses or prerecorded odor plumes were deployed in a constant flow of air. For both environments, our results indicate that the gas concentration is encoded in—and inversely proportional to—the time difference of analog spikes emerging out of two parallel pathways. The resulting neuromorphic nose could enable data-efficient, real-time robotic plume navigation systems, advancing the capabilities of odor source localization in applications such as environmental monitoring and search-and-rescue.